Support tensor machine with dynamic penalty factors and its application to the fault diagnosis of rotating machinery with unbalanced data
Mechanical Systems and Signal Processing(2020)
摘要
•A new tensor classifier called DC-STM is proposed and applied to the fault diagnosis of rotating machinery.•Dynamic penalty factors are introduced into DC-STM to solve the unbalanced data problem.•A tensor kernel function is used in the model of DC-NSTM to deal with the nonlinear separable problem.•Third-order feature tensors are constructed by wavelet time-frequency grayscale images.•Experimental results show that DC-STM is superior to the classifiers of the vector space.
更多查看译文
关键词
Rotating machinery,Fault diagnosis,Support tensor machine,Unbalanced data,Dynamic penalty factors
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络